Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8868
    Prev
    Next
    INDEX
    Explanations

    words related to cognitive processes and the brain

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cognitive functions and brain processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     è£ıè
    -0.78
    é¾
    -0.75
    å°Ĩ
    -0.74
     Izan
    -0.74
    hw
    -0.73
    iannopoulos
    -0.72
     Collider
    -0.71
     Credits
    -0.70
     ashes
    -0.70
    osponsors
    -0.68
    POSITIVE LOGITS
     cognition
    1.48
     cognitive
    1.26
     spatial
    1.24
     comprehension
    1.23
     perceptual
    1.22
     reasoning
    1.19
     memory
    1.17
     sensory
    1.16
     learning
    1.15
     empathy
    1.15
    Activations Density 0.261%

    No Known Activations